Detecting changes with multiple sensors has received significant attention in the literature. In many practical applications such as critical infrastructure monitoring and modeling of disease spread, a useful change propagation model is one where change eventually happens at all sensors, but where not all sensors witness change at the same time-instant. While the known change propagation dynamics was studied before, this paper studies a more general setting of unknown change propagation pattern (trajectory) in both centralized and decentralized settings with the goal of detecting the first time-instant any sensor witnesses a change. Using the dynamic programming framework, the optimal solution structures are derived and in the special rare-change regime, several more practical solutions are proposed. Under certain conditions, the first-order asymptotic optimality of a proposed algorithm called multichart test is shown as the false alarm probability vanishes. Moreover, low-complexity solutions are proposed based on online estimation of the change propagation pattern. Numerical studies illustrate that the proposed detectors offer near-optimal performance. Furthermore, in the decentralized setting, the level-crossing sampling is proposed for sampling and transmission of local statistics that significantly improves the detection performance using the same amount of communication resources compared to the conventional uniform-in-time sampling.
Multisensor Sequential Change Detection With Unknown Change Propagation Pattern
IEEE Transactions on Aerospace and Electronic Systems ; 55 , 3 ; 1498-1518
2019-06-01
1317034 byte
Article (Journal)
Electronic Resource
English
Multisensor Distributed Sequential Detection
Online Contents | 1994
|Multisensor distributed sequential detection
IEEE | 1994
|